{"id":"W137061674","doi":"10.63317/2tjb7zqm2qsv","title":"Using the Web as a Linguistic Resource to Automatically Correct Lexico-Syntactic Errors","year":2008,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Natural language processing; Sentence; Focus (optics); Artificial intelligence; Context (archaeology); Grammar; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003479355,0.0001746905,0.0001730974,0.0001346189,0.0003835975,0.0001828596,0.001466079,0.00006963444,0.00003751411],"category_scores_gemma":[0.001546735,0.0001118999,0.00006287352,0.0007547475,0.00008439105,0.0001779185,0.0004716967,0.0002728423,0.0001002971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009583413,"about_ca_system_score_gemma":0.0002484075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001540774,"about_ca_topic_score_gemma":0.0000151515,"domain_scores_codex":[0.9984897,0.000103,0.0002461582,0.0003776186,0.0004297752,0.000353722],"domain_scores_gemma":[0.9985981,0.0003097707,0.00008173293,0.0007520563,0.0001224532,0.0001358781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001825073,0.0007923288,0.001713595,0.0002921419,0.0002170976,0.003935942,0.06340665,0.001023266,0.08936942,0.6650445,0.07346759,0.1005549],"study_design_scores_gemma":[0.0003797512,0.0004649731,0.0001666932,0.0003679182,0.00004664089,0.004035551,0.0002364001,0.867176,0.05553767,0.04381139,0.0265521,0.001224939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03152272,0.0002937055,0.9491124,0.002787777,0.0002636257,0.0003366615,5.222765e-7,0.002204793,0.01347782],"genre_scores_gemma":[0.5199733,0.000001098845,0.4767364,0.002480143,0.00005650515,0.000007295115,2.012323e-7,0.00001106171,0.0007340451],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8661527,"threshold_uncertainty_score":0.4563147,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03857461495009921,"score_gpt":0.3190949380143581,"score_spread":0.2805203230642588,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}